A Refined Approach of Image Retrieval Using RBF-SVM Classifier
Mohd Aquib Ansari, Manish Dixit · International Journal of Signal Processing Image Processing and Pattern Recognition · 2017
In recent trends, Content Based image retrieval (CBIR) is a vast as well as an attractive research area, where various active researchers are doing their respective work.It is the widely used technique of image retrieval, which enables the system to retrieve the relevant images from wide range of image database following the user's query image.In designing of good CBIR system, to select an appropriate feature descriptor which can represent the image content efficiently is not an easy task.In this proposed work, an efficient CBIR system has been suggested for image retrieval which mainly focused on the classification of image database as well as appropriate image representation.Here, we used HSV histogram, discrete wavelet transform and local as well as global edge histogram descriptor with SVM classifier based on RBF kernel function.In the scheme of feature evaluation, first extracted quantized HSV histogram to extract the color feature of image, applied discrete wavelet transform on the each component (Hue, Saturation and value components) of the HSV image to extract the complex texture pattern of image and for evaluation of geometric as well as spatial information of image applied local as well as global edge histogram descriptor on the Value component of HSV Image.After combining the all feature vectors, SVM Classifier applied on the image feature database to classify the images appropriately.For experimental analysis, this proposed methodology applied on the Wang image database of 1-k images with 10 categories.On the basis of Precision, recall and accuracy, it is found that this system, based on classification, is performing well in comparison to other existing proposed schemes.